Related papers: CATALOG: A Camera Trap Language-guided Contrastive…

Contrastive learning has been applied to Human Activity Recognition (HAR) based on sensor data owing to its ability to achieve performance comparable to supervised learning with a large amount of unlabeled data and a small amount of labeled…

Phrase grounding, the problem of associating image regions to caption words, is a crucial component of vision-language tasks. We show that phrase grounding can be learned by optimizing word-region attention to maximize a lower bound on…

Wildlife monitoring is crucial for studying biodiversity loss and climate change. Camera trap images provide a non-intrusive method for analyzing animal populations and identifying ecological patterns over time. However, manual analysis is…

State-of-the-art pre-trained image models predominantly adopt a two-stage approach: initial unsupervised pre-training on large-scale datasets followed by task-specific fine-tuning using Cross-Entropy loss~(CE). However, it has been…

Learning good representations involves capturing the diverse ways in which data samples relate. Contrastive loss - an objective matching related samples - underlies methods from self-supervised to multimodal learning. Contrastive losses,…

Visual localization is a crucial component in the application of mobile robot and autonomous driving. Image retrieval is an efficient and effective technique in image-based localization methods. Due to the drastic variability of…

The steady rise of online shopping goes hand in hand with the development of increasingly complex ML and NLP models. While most use cases are cast as specialized supervised learning problems, we argue that practitioners would greatly…

Current state-of-the-art object-centric models use slots and attention-based routing for binding. However, this class of models has several conceptual limitations: the number of slots is hardwired; all slots have equal capacity; training…

Contrastive learning (CL) is a popular technique for self-supervised learning (SSL) of visual representations. It uses pairs of augmentations of unlabeled training examples to define a classification task for pretext learning of a deep…

Medical image segmentation has been widely recognized as a pivot procedure for clinical diagnosis, analysis, and treatment planning. However, the laborious and expensive annotation process lags down the speed of further advances.…

High-performance Multimodal Large Language Models (MLLMs) are heavily dependent on data quality. To advance fine-grained image recognition within MLLMs, we introduce a novel data synthesis method inspired by contrastive learning and image…

Overlapping sound events are ubiquitous in real-world environments, but existing end-to-end sound event detection (SED) methods still struggle to detect them effectively. A critical reason is that these methods represent overlapping events…

In this study, we propose a feature extraction framework based on contrastive learning with adaptive positive and negative samples (CL-FEFA) that is suitable for unsupervised, supervised, and semi-supervised single-view feature extraction.…

To overcome the domain gap between synthetic and real-world datasets, unsupervised domain adaptation methods have been proposed for semantic segmentation. Majority of the previous approaches have attempted to reduce the gap either at the…

Instance contrast for unsupervised representation learning has achieved great success in recent years. In this work, we explore the idea of instance contrastive learning in unsupervised domain adaptation (UDA) and propose a novel Category…

The Contrastive Language-Image Pre-training (CLIP) Model is a recently proposed large-scale pre-train model which attracts increasing attention in the computer vision community. Benefiting from its gigantic image-text training set, the CLIP…

Pre-training vision-language models with contrastive objectives has shown promising results that are both scalable to large uncurated datasets and transferable to many downstream applications. Some following works have targeted to improve…

Conditional image generation is the task of generating diverse images using class label information. Although many conditional Generative Adversarial Networks (GAN) have shown realistic results, such methods consider pairwise relations…

Detecting small targets in sea clutter is challenging due to dynamic maritime conditions. Existing solutions either model sea clutter for detection or extract target features based on clutter-target echo differences, including statistical…

Contrastive learning has recently demonstrated superior performance to supervised learning, despite requiring no training labels. We explore how contrastive learning can be applied to hundreds of thousands of unlabeled Mars terrain images,…